微生物发酵过程的神经网络左右逆协同控制方法（英文）  

Cooperative left and right ANN inversions control method of microbial fermentation with directly immeasurable variables

作　　者：丁煜函[1] 梅从立[1] 陈旭[1] 江辉[1] 杨培锁 

机构地区：[1]江苏大学电气信息工程学院,江苏镇江212013

出　　处：《计算机与应用化学》2016年第11期1182-1186,共5页Computers and Applied Chemistry

基　　金：Supported by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD[2011]6);the Natural Science Foundation of Jiangsu Province of China(BK20130531,BK20151345)~~

摘　　要：微生物发酵生产过程是一种高度非线性、不确定的系统,发酵过程中很多关键变量难以在线直接测量,严重影响了这些系统的控制和优化,给这些生产过程的产品产量和质量的提高带来了严重的障碍。本文采用右逆控制方法实现对原系统的线性化解耦,采用左逆软测量方法来实现对难以直接测量的关键变量的软测量,并将软测量得到的结果作为右逆控制方法所需要的反馈变量,实现对微生物发酵的控制。这种左右逆协同工作,实现系统控制的方法可称为协同控制方法,所构造的控制器称为左右逆协同控制器。由于微生物发酵过程的强非线性特性,采用神经网络加动态环节(微分器、积分器)的方法来构造上述的左右逆协同控制器。仿真结果表明,这种左右逆协同控制方法能很好地实现对含有不直接可测变量的微生物发酵过程的控制。To realize the control of microbial fermentation with directly immeasurable variables, we propose a cooperative left and right inversion control method, which use right inversion method to linearize and decouple the original system and use left inversion method to obtain the directly immeasurable variables. This method makes the left inversion and right inversion to control a system cooperatively, so it can be called the cooperative left and right inversions control method. The corresponding controller can be called cooperative left and inversions controller. To overcome the difficulties in realizing the two inversions, Artificial Neural Networks （ANNs） are adopted to construct the above controller. Simulation results indicate that, the method presented in this paper can well implement the control of such systems as microbial fermentation with directly immeasurable variables.

关 键 词：左右逆 协同控制 神经网络 微生物发酵 不可测变量 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]